Keras卷积自动编码器不工作

我从Keras笔者就在这里测试的卷积的自动编码： https://blog.keras.io/building-autoencoders-in-keras.html Keras卷积自动编码器不工作

但我有这样的问题：

Exception: Error when checking model target: expected convolution2d_7 to have shape (None, 8, 32, 1) but got array with shape (60000, 1, 28, 28)

我准确的，我已经设置好的最后一个conv层中的字段'border_mode ='same''。所以，我真的不从那里来，从知道.. 以下是摘要：

Layer (type)      Output Shape   Param #   Connected to      
     ==================================================================================================== 
input_1 (InputLayer)    (None, 1, 28, 28)  0            
____________________________________________________________________________________________________ 
convolution2d_1 (Convolution2D) (None, 1, 28, 16)  4048  input_1[0][0]      
____________________________________________________________________________________________________ 
maxpooling2d_1 (MaxPooling2D) (None, 1, 14, 16)  0   convolution2d_1[0][0]    
     ______________________________________________________________________________ ______________________ 
convolution2d_2 (Convolution2D) (None, 1, 14, 8)  1160  maxpooling2d_1[0][0]    
____________________________________________________________________________________________________ 
maxpooling2d_2 (MaxPooling2D) (None, 1, 7, 8)  0   convolution2d_2[0][0]    
____________________________________________________________________________________________________ 
convolution2d_3 (Convolution2D) (None, 1, 7, 8)  584   maxpooling2d_2[0][0]    
____________________________________________________________________________________________________ 
maxpooling2d_3 (MaxPooling2D) (None, 1, 4, 8)  0   convolution2d_3[0][0]    
____________________________________________________________________________________________________ 
convolution2d_4 (Convolution2D) (None, 1, 4, 8)  584   maxpooling2d_3[0][0]    
____________________________________________________________________________________________________ 
upsampling2d_1 (UpSampling2D) (None, 2, 8, 8)  0   convolution2d_4[0][0]    
____________________________________________________________________________________________________ 
convolution2d_5 (Convolution2D) (None, 2, 8, 8)  584   upsampling2d_1[0][0]    
____________________________________________________________________________________________________ 
upsampling2d_2 (UpSampling2D) (None, 4, 16, 8)  0   convolution2d_5[0][0]    
____________________________________________________________________________________________________ 
convolution2d_6 (Convolution2D) (None, 4, 16, 16)  1168  upsampling2d_2[0][0]    
____________________________________________________________________________________________________ 
upsampling2d_3 (UpSampling2D) (None, 8, 32, 16)  0   convolution2d_6[0][0]    
______________________________________________________________________________ ______________________ 

convolution2d_7 (Convolution2D) (None, 8, 32, 1)  145    

upsampling2d_3[0][0]    
==================================================================================================== 
Total params: 8273 
____________________________________________________________________________________________________

来源

2016-12-27 Pusheen_the_dev

此问题可能是以下情况的重复：http://stackoverflow.com/questions/39848466/tensorflow-keras-convolution2d-valueerror-filter-must-not-be-larger-than-t?noredirect=1#comment67013494_39848466 –

嗨，我看到这个线程，的确，dim_ordering需要更改为theano dim。（1，x，x）但是，问题保持不变，现在，网络期望（1,28,28），但得到（1,32,32）我明白这是因为最后一个upsampling层，但是最后一个带3x3大小过滤器的conv应该安排不？ –

终于找到了答案。我认为本教程的创建者使用32x32 MNIST图像而不是28x28进行了测试。

因为，当添加到最后一个conv layer border_mode ='same'时，您将得到一个输出形状（32,32,1）因此，要获得良好的输出（28,28,1），您需要将border_mode ='valid'添加到前一个conv层。

总结：将尺寸排序更正为28x28x1而不是1x28x28。然后将边框模式添加到最后一个conv层最后添加对最后一个conv层有效的边框模式。

希望这会有所帮助。

来源

2016-12-27 15:54:41

Keras卷积自动编码器不工作

回答

相关问题